蔡有城 (Youcheng Cai)

个人简介

蔡有城，男，现为中国科学技术大学数学科学学院博士后。主要研究领域为三维视觉，神经渲染，三维生成。近年来，在SIGRAPH/CVPR/TVCG等一区国际期刊及CCF-A类会议上发表论文多篇。

教育与工作经历

• 2023.9 - 至今：中国科学技术大学，数学科学学院，博士后
• 2018.9 - 2023.6：合肥工业大学，计算机科学与技术，博士
• 2014.9 - 2018.6：合肥工业大学，信息与计算科学，学士

发表论文

• Youcheng Cai, Fan gao, Yibo Zhao, Li Li* and Ligang Liu . AHC-NeRF: Autonomous, High-Quality Neural Reconstruction of Two-Layer Complex Nested Transparent Objects, IEEE Transactions on Visualization and Computer Graphics, 2026.
• Jincheng Hu, Yuxiao Wu, Youcheng Cai*, and Ligang Liu. CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
• Yifan Mo, Youcheng Cai*, and Ligang Liu. Plug-and-Play PDE Optimization for 3D Gaussian Splatting: Toward High-Quality Rendering and Reconstruction, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
• Runze Wang, Yuxuan Song, Youcheng Cai*, and Ligang Liu. STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
• Yikai Huang, Renmin Han, Yuxuan Wang, Youcheng Cai and Ligang Liu*. Spatial-SAM: Spatially Consistent 3D Electron Microscopy Segmentation with SDF Memory and Semi-Supervised Learning, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
• Fan Gao, Yibo Zhao, Youcheng Cai*, Ligang Liu. Hash-NURF: Efficient Nested Transparent Object Reconstruction Using Multi-Resolution Hash Encoding. The Visual Computer 42(4) (2026): 1432-2315.
• Junyan Qi, Youcheng Cai*, Ligang Liu. DragMV: Interactive drag-style manipulation on multi-view images. Computers & Graphics (2025): 104344.
• Huangsheng Du, Youcheng Cai*, Yutian Zhu, Peifeng Li, Ligang Liu. Importance Sampling Guided Neural Radiosity. Computers & Graphics (2025): 104472.
• Dong Wang, Youcheng Cai, Yiming Tang, Wenjun Xie*, Xiaoping Liu. MLENet: Multi-level efficient network based on single-scale feature extraction for human keypoint estimation. Expert Systems with Applications (2025): 130092.
• Ping Lu, Youcheng Cai*, Jiale Yang, Dong Wang, Tingting Wu. Uanet: uncertainty-aware cost volume aggregation-based multi-view stereo for 3D reconstruction. The Visual Computer 41(7) (2025): 4567-4580.
• Youcheng Cai, Runshi Li, and Ligang Liu*. "Mv2mv: Multi-view image translation via view-consistent diffusion models." ACM Transactions on Graphics (TOG) 43.6 (2024): 1-12.
• Youcheng Cai, Lin Li, Dong Wang, Xinjie Li, Xiaoping Liu. HTMatch: An efficient hybrid transformer based graph neural network for local feature matching. Signal Processing 204 (2023): 108859.
• Youcheng Cai, Lin Li, Dong Wang, Xiaoping Liu. MFNet: Multi-level fusion aware feature pyramid based multi-view stereo network for 3D reconstruction. Applied Intelligence 53(4) (2023): 4289-4301.
• Youcheng Cai, Lin Li, Dong Wang, Xintao Huang, Xiaoping Liu. GlcMatch: global and local constraints for reliable feature matching. The Visual Computer 39(7) (2023): 2555-2570.